What if they had made northwood at 90nm?

[Cooler]

Originally posted by: Fox5
I'd say Netburst is a better design than the Athlon core, longer IS better than wider. Typically parallel problems can easily be made sequential, but the reverse isn't true, so Netburst should have a higher efficiency than Athlon. (when you consider Athlon has additional execution units)

And it's not like the Athlon and P-M's don't feature fairly long pipelines of their own.

BTW, didn't the final P3s have severe heat problems as well? Maybe we'll see a P4 based design come back in a few generations.

it could happen might be just glich in presccot desgin.

 

[jiffylube1024]

They did shrink Northwood to 90nm. It was called Prescott. It had problems running above 2.8 Ghz due to a problem with heat (thermal density increases with die shrinks), and missed its deadline with nothing to show for it.

The Intel design team, stuck with a die-shrunk Northwood that couldn't run above 2.8 Ghz (and hotter than a similar clocked Northwood at 130nm), had to resort to increasing the pipeline length in order to get clock speed to increase. And it still took months to sort out other issues.

Northwood's 90nm die shrink was one of the first signs of a processor design hitting a wall after a "simple" die shrink, which is why new techs like SOI, strained silicon, etc. are necessary to compliment die shrinks to keep heat under control.

 

[Hacp]

Originally posted by: jiffylube1024
They did shrink Northwood to 90nm. It was called Prescott. It had problems running above 2.8 Ghz due to a problem with heat (thermal density increases with die shrinks), and missed its deadline with nothing to show for it.

The Intel design team, stuck with a die-shrunk Northwood that couldn't run above 2.8 Ghz (and hotter than a similar clocked Northwood at 130nm), had to resort to increasing the pipeline length in order to get clock speed to increase. And it still took months to sort out other issues.

Northwood's 90nm die shrink was one of the first signs of a processor design hitting a wall after a "simple" die shrink, which is why new techs like SOI, strained silicon, etc. are necessary to compliment die shrinks to keep heat under control.

Actually, it was due to power leakage. They seemed to have found a solution to it now, but if they found the solution earlier, then they would have had a better launch with a 90nm northwood than prescott.

 

[DrMrLordX]

Originally posted by: jiffylube1024
They did shrink Northwood to 90nm. It was called Prescott. It had problems running above 2.8 Ghz due to a problem with heat (thermal density increases with die shrinks), and missed its deadline with nothing to show for it.

The Intel design team, stuck with a die-shrunk Northwood that couldn't run above 2.8 Ghz (and hotter than a similar clocked Northwood at 130nm), had to resort to increasing the pipeline length in order to get clock speed to increase. And it still took months to sort out other issues.

Northwood's 90nm die shrink was one of the first signs of a processor design hitting a wall after a "simple" die shrink, which is why new techs like SOI, strained silicon, etc. are necessary to compliment die shrinks to keep heat under control.

That isn't really true. Prescott had a longer pipeline. It was different enough to be its own new core.

 

[DrMrLordX]

Originally posted by: dmens
Was everyone carping about netburst when northwood was doing well? It had a 25 stage pipeline, and even with all the extra high activity transistor gate width of a netburst pipeline, its thermals weren't that bad. In fact, if intel had the foresight to let the experienced northwood team (instead of another team which will go unnamed) handle the prescott project and slapped a memory controller on there, it'd be doing pretty well against A64. Prescott was netburst style, but it was a pretty awful implementation. Same goes for the abandoned tejas (again, that was not the northwood team).

I don't think so many people were carping about Netburst back when the 3.2C was released, no. At the time, it was the overall fastest x86 processor on the market. Intel was tops in performance, and AMD was struggling to catch up with their relatively lame desktop Barton chips. The 3200+ was a major disappointment to a lot of folks.

I have to wonder why Intel didn't let the Northwood team continue the development of Netburst-based architectures. It was pretty obvious to me that Netburst's various incarnations always struggled in some fashion until Northwood came along . . .

 

[F1shF4t]

Didn't the Northwood have a 20 stage pipeline not 25?

 

[Hacp]

Originally posted by: Dark Cupcake
Didn't the Northwood have a 20 stage pipeline not 25?

Yes

 

[Maximilian]

So what happened to the "northwood team"?? Where did they go?

 

[DrMrLordX]

Kokomo.